Artificial Neural Network Backpropagation with Particle Swarm Optimization for Crude Palm Oil Price Prediction

Abstract

Crude Palm Oil (CPO) is one of the plantation commodities provide the greatest contribution to Indonesia's foreign exchange. Because this plantation is one of the vegetable oil-producing plants with a high economic value. Therefore, the accuracy of the forecasting approaches in predicting the CPO prices is becoming the matter into concerns. This study aims to design a method of forecasting the price level for CPO. Neural Network Backpropagation (NN-BP) has been seen as a successful model in many systems recently. In this paper, we will apply Neural Network Backpropagation with a powerful stochastic optimization technique called Particle Swarm Optimization (PSO) to optimize the weight on NN-BP of Crude Palm Oil commodity price. The proposed method is a prediction model using an algorithm which combining particle swarm optimization (PSO) with Neural Network back-propagation (NN-BP) namely PSO-BP. The experimental results show that the proposed PSO-BP algorithm is better than standard Artificial Neural Network Backpropagation for accurate prediction and error convergence by providing better RMSE values.